Title :
A multilevel stereo correspondence searching strategy for real-time obstacle detection using linear cameras
Author :
Hariti, M. ; Ruichek, Y. ; Koukam, A.
Author_Institution :
Laboratoire Syst. et Transp., Universite de Technol. de Belfort-Montbeliard, Belfort, France
Abstract :
This paper presents a method, which performs edge stereo matching at different levels, from significant edges to less significant ones. At each level, the process starts by selecting significant edges with respect to their gradient magnitude. The selected edges are then matched and the obtained pairs are used for matching less significant edges in the next level. The matching procedure is based on a voting scheme by using local and global constraints. The performance of the proposed stereo matching method is evaluated for real-time obstacle detection in front of a vehicle using linear cameras.
Keywords :
cameras; edge detection; image matching; object detection; real-time systems; stereo image processing; vehicle dynamics; edge stereo matching; linear cameras; linear stereo vision; multilevel stereo correspondence searching strategy; real-time obstacle detection; vehicle; voting scheme; Cameras; Computer vision; Data mining; Feature extraction; Image edge detection; Object detection; Stereo vision; Vehicle detection; Vehicles; Voting;
Conference_Titel :
Networking, Sensing and Control, 2004 IEEE International Conference on
Print_ISBN :
0-7803-8193-9
DOI :
10.1109/ICNSC.2004.1297084